The relationship between dynamic programming and active inference: the discrete, finite-horizon case.
Lancelot Da CostaNoor SajidThomas ParrKarl J. FristonRyan SmithPublished in: CoRR (2020)
Keyphrases
- finite horizon
- dynamic programming
- infinite horizon
- optimal policy
- markov decision processes
- inventory models
- multistage
- inventory control
- optimal stopping
- single product
- optimal control
- single item
- np hard
- state space
- long run
- finite state
- lost sales
- yield management
- markov decision process
- average cost
- production planning
- machine learning
- hidden markov models
- search algorithm
- reinforcement learning
- bayesian networks
- learning algorithm